Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    attract auction children tuple

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    を
    0.41
    的に
    0.39
     minerals
    0.39
    нет
    0.39
     о
    0.38
    级别
    0.37
    ሉ።
    0.37
    および
    0.36
    (+
    0.36
    级别的
    0.36
    POSITIVE LOGITS
     esimerkiksi
    0.45
     However
    0.41
    Eine
    0.41
     weiteren
    0.40
     exempel
    0.40
     Beberapa
    0.40
    Bhar
    0.40
     nekaj
    0.39
     Eine
    0.39
     ఈ
    0.38
    Act Density 0.000%

    No Known Activations